Authors:
Maxim Sidorov
1
;
Christina Brester
2
;
Eugene Semenkin
2
and
Wolfgang Minker
1
Affiliations:
1
Ulm University, Germany
;
2
Siberian State Aerospace University, Russian Federation
Keyword(s):
Speech-based Emotion Recognition, Speech-based Speaker and Gender Identification, Neural Network, Genetic Algorithm-based Feature Selection, Speech Corpora Analysis.
Related
Ontology
Subjects/Areas/Topics:
Adaptive Signal Processing and Control
;
Artificial Intelligence
;
Computational Intelligence
;
Evolutionary Computing
;
Genetic Algorithms
;
Informatics in Control, Automation and Robotics
;
Intelligent Control Systems and Optimization
;
Signal Processing, Sensors, Systems Modeling and Control
;
Soft Computing
Abstract:
While the implementation of existing feature sets and methods for automatic speaker state analysis has already
achieved reasonable results, there is still much to be done for further improvement. In our research, we tried
to carry out speech analysis with the self-adaptive multi-objective genetic algorithm as a feature selection
technique and with a neural network as a classifier. The proposed approach was evaluated using a number of
multi-language speech databases (English, German and Japanese). According to the obtained results, the developed
technique allows an increase in emotion recognition performance by up to 6.2% relative improvement
in average F-measure, up to 112.0% for the speaker identification task and up to 6.4% for the speech-based
gender recognition, having approximately half as many features.